Qwen3-Coder-Next
Released2026-02-02Size80B · 3B activeArchitecturehybrid linear attnLicenseapache-2.0AA rank#63 of 75
Files and memory at 8K context
| Quant | File | Files | + KV + runtime | Smallest fit | Source |
|---|---|---|---|---|---|
| Q4_K_M unsloth/Qwen3-Coder-Next-GGUF | 45.20 GiB | 1 | 46.4 GiB+ | 48 GB GPU | HF files |
| Q5_K_M unsloth/Qwen3-Coder-Next-GGUF | 52.94 GiB | 3 | 54.1 GiB+ | 64 GB GPU | HF files |
| Q8_0 unsloth/Qwen3-Coder-Next-GGUF | 78.99 GiB | 3 | 80.2 GiB+ | 96 GB GPU | HF files |
| BF16 unsloth/Qwen3-Coder-Next-GGUF | 149 GiB | 4 | 150 GiB+ | 192 GB GPU | HF files |
| MLX 4-bit mixed precision mlx-community/Qwen3-Coder-Next-4bit | 41.76 GiB | 9 | 43.0 GiB+ | 64 GB Mac | HF files |
| MLX 8-bit mixed precision mlx-community/Qwen3-Coder-Next-8bit | 78.84 GiB | 17 | 80.0 GiB+ | 128 GB Mac | HF files |
No verified file: FP16. Sizes are exact file bytes (text weights; projectors listed separately). “+” = recurrent state or other terms unknown. Smallest fit adds 0.5 GiB spare; Macs use 75% of memory.
Quality
Artificial Analysis Intelligence Index
9.2
Variant: Qwen3 Coder Next · observed 2026-10-17 · source
Rank #63 of 75 researched 2026 models.
Arena text rating
Unknown
Scores describe the evaluated hosted variant, not each quantized file. AA and Arena are never averaged.
Reported speeds 14
Reported by the linked sources, not reproduced by LocalFit. All rows in the speed database